{"id":"CVE-2026-17557","aliases":["EUVD-2026-107135","GHSA-xphj-jg67-vf2w"],"status":"published","title":"Lm-evaluation-harness: lm-evaluation-harness: ssrf via job-spec model.url with bearer credential forwarding","description":"A flaw was found in the `lm-evaluation-harness` component of Red Hat OpenShift AI. An authenticated user, able to submit an evaluation job, could exploit this by providing a malicious model URL in the `JobSpec`. This vulnerability allows for the disclosure of the tenant's model authentication secret to an attacker-controlled external listener. Additionally, it enables Server-Side Request Forgery (SSRF) attacks against internal network endpoints reachable from the evaluation job pod.","severity":{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N","level":"medium","assessor":"cna","from":"cve"},"epss":{"day":"2026-11-10","score":0.00327,"percentile":0.26068,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":false,"fix_available":false},"cwes":["CWE-918"],"published":"2026-10-21T07:59:10Z","modified":"2026-10-22T15:25:35Z","products":[{"vendor":"red hat","product":"red hat openshift ai (rhoai)"}],"references":[{"url":"https://access.redhat.com/security/cve/CVE-2026-17557","tags":["vdb-entry","x_refsource_REDHAT"]},{"url":"https://bugzilla.redhat.com/show_bug.cgi?id=2507452","tags":["issue-tracking","x_refsource_REDHAT"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-17557"},{"url":"https://github.com/advisories/GHSA-xphj-jg67-vf2w"}],"sources":{"cve":[{"id":"CVE-2026-17557","title":"Lm-evaluation-harness: lm-evaluation-harness: ssrf via job-spec model.url with bearer credential forwarding","description":"A flaw was found in the `lm-evaluation-harness` component of Red Hat OpenShift AI. An authenticated user, able to submit an evaluation job, could exploit this by providing a malicious model URL in the `JobSpec`. This vulnerability allows for the disclosure of the tenant's model authentication secret to an attacker-controlled external listener. Additionally, it enables Server-Side Request Forgery (SSRF) attacks against internal network endpoints reachable from the evaluation job pod.","status":"published","published":"2026-10-21T07:59:10.543Z","modified":"2026-10-21T13:38:59.538Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N","level":"medium","assessor":"cna"}],"cwes":["CWE-918"],"updated_at":"2026-11-02T14:19:54.84674Z"}],"euvd":[{"id":"EUVD-2026-107135","description":"A flaw was found in the `lm-evaluation-harness` component of Red Hat OpenShift AI. An authenticated user, able to submit an evaluation job, could exploit this by providing a malicious model URL in the `JobSpec`. This vulnerability allows for the disclosure of the tenant's model authentication secret to an attacker-controlled external listener. Additionally, it enables Server-Side Request Forgery (SSRF) attacks against internal network endpoints reachable from the evaluation job pod.","status":"published","published":"2026-10-21T07:59:10Z","modified":"2026-10-21T13:38:59Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N","level":"medium"}],"updated_at":"2026-11-02T16:59:37.063674Z"}],"ghsa":[{"id":"GHSA-xphj-jg67-vf2w","title":"A flaw was found in the `lm-evaluation-harness` component of Red Hat OpenShift AI. An...","description":"A flaw was found in the `lm-evaluation-harness` component of Red Hat OpenShift AI. An authenticated user, able to submit an evaluation job, could exploit this by providing a malicious model URL in the `JobSpec`. This vulnerability allows for the disclosure of the tenant's model authentication secret to an attacker-controlled external listener. Additionally, it enables Server-Side Request Forgery (SSRF) attacks against internal network endpoints reachable from the evaluation job pod.","status":"published","published":"2026-10-21T09:30:29Z","modified":"2026-10-21T09:30:30Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N","level":"medium"}],"cwes":["CWE-918"],"updated_at":"2026-11-02T15:14:09.061875Z"}],"nvd":[{"id":"CVE-2026-17557","description":"A flaw was found in the `lm-evaluation-harness` component of Red Hat OpenShift AI. An authenticated user, able to submit an evaluation job, could exploit this by providing a malicious model URL in the `JobSpec`. This vulnerability allows for the disclosure of the tenant's model authentication secret to an attacker-controlled external listener. Additionally, it enables Server-Side Request Forgery (SSRF) attacks against internal network endpoints reachable from the evaluation job pod.","status":"published","published":"2026-10-21T08:16:43.09Z","modified":"2026-10-22T15:25:35.333Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N","level":"medium","assessor":"secondary"}],"cwes":["CWE-918"],"updated_at":"2026-11-02T14:13:02.045979Z"}]}}